© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 13899
    Prev
    Next
    INDEX
    Explanations

    something or the idea that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģ©
    -0.08
     ÑģколÑĮко
    -0.08
    sWith
    -0.08
     ÙĩÙħÛĮÙĨ
    -0.08
     Lambert
    -0.08
    672
    -0.08
    azi
    -0.08
    ynom
    -0.07
    eon
    -0.07
    eted
    -0.07
    POSITIVE LOGITS
     something
    0.69
    something
    0.53
     Something
    0.50
    Something
    0.47
    omething
    0.44
     iets
    0.43
     etwas
    0.42
    æŁIJ
    0.36
     nÄĽco
    0.35
     algo
    0.34
    Activations Density 0.410%

    No Known Activations